RATIONALE: Drugs used in chemotherapy use different ways to stop tumor cells from dividing so they stop growing or die. It is not yet known if combination chemotherapy is more effective than no further treatment for non-small cell lung cancer.

PURPOSE: Randomized phase III trial to compare the effectiveness of vinorelbine plus cisplatin with that of no further therapy in treating patients who have stage I or stage II non-small cell lung cancer that has been completely removed during surgery.

OBJECTIVES: I. Compare the duration of overall and disease-free survival in patients with completely resected non-small cell lung cancer (NSCLC) randomized to adjuvant chemotherapy with vinorelbine and cisplatin versus observation only. II. Confirm the prognostic significance of ras mutations when present in the primary tumor. III. Provide a comprehensive tumor bank linked to a clinical database for the further study of molecular markers in resected NSCLC. IV. Measure and compare the health-related quality of life of patients on both treatment arms. V. Evaluate any toxicity related to this treatment regimen.

OUTLINE: This is a randomized study. Patients are stratified according to participating institution, nodal status (N0 vs N1), and ras mutation status of primary tumor (absent vs present vs unknown). Patients are randomized to one of two treatment arms. Arm I: Patients are evaluated at 3 and 6 months after randomization. Arm II: Patients receive vinorelbine IV over 6-10 minutes weekly for 16 weeks. Patients also receive cisplatin IV on days 1 and 8 every 4 weeks for a total of 4 courses. Treatment continues in the absence of disease progression or unacceptable toxicity. Quality of life is assessed at Canadian centers. Quality of life assessments are optional for ECOG and SWOG centers. Patients are followed every 3 months for 2 years and then every 6 months thereafter.

PROJECTED ACCRUAL: A total of 450 patients will be accrued for this study within 6.75 years.

DISEASE CHARACTERISTICS: Histologically confirmed primary non-small cell lung cancer that is completely resected No mixed small and non-small cell histologies Pathologic T2 N0 or T1-2 N1 T1 N1 and T2 N1 only for CALGB institutions Removal of all gross disease with negative resection margins by lobectomy, sleeve resection, bilobectomy, or pneumonectomy (based on intraoperative findings) No segmentectomy or wedge resection Complete mediastinal lymph node resection or sampling required at primary tumor resection, with minimum levels of nodal sampling as follows: Primary in right upper lobe - levels 4, 7, 10 Primary in right middle lobe - levels 4, 7, 10 Primary in right lower lobe - levels 4, 7, 9, 10 Primary in left upper lobe - levels 5, 6, 7, 10 Primary in left lower lobe - levels 7, 9, 10 If complete mediastinal lymph node resection has not been undertaken, any mediastinal lymph node which measured 1.5 cm or more on presurgical CT scan must have been biopsied and found to be free of metastatic involvement Disease at nodal station 10 (tracheobronchial angle) is considered N2 disease for this trial and is not eligible No more than one discrete primary tumor No bronchoalveolar carcinoma with lobar or multilobar involvement Discrete solitary radiological mass or nodule eligible Snap frozen fresh primary tumor tissue must be submitted to Lung Cancer Tumor Bank within 14 days after surgery by selected Canadian centers Others to submit representative paraffin block within 2 months of surgery

PATIENT CHARACTERISTICS: Age: 18 and over (lower age limit determined by individual center) Performance status: ECOG 0 or 1 Life expectancy: Not specified Hematopoietic: Absolute granulocyte count greater than 2,000/mm3 Platelet count greater than 100,000/mm3 Hemoglobin greater than 10.0 g/dL Hepatic: Bilirubin no greater than 1.25 times normal AST/ALT no greater than 1.25 times normal Alkaline phosphatase no greater than 1.25 times normal Renal: Creatinine no greater than 1.7 mg/dL Cardiovascular: No history of congestive heart failure or other cardiac abnormality that may preclude hydration necessary for cisplatin administration Other: No active pathologic condition that would preclude study No active uncontrolled infection No history of psychiatric or neurologic disorder that would preclude study No prior breast cancer, melanoma, or hypernephroma No other malignancy within the past 5 years except adequately treated nonmelanomatous skin cancer or carcinoma in situ of the cervix Not pregnant or nursing Fertile patients must use effective contraception Ability to tolerate treatment (based on consultation between the thoracic surgeon and a medical oncologist or hematologist) and available for follow-up

PRIOR CONCURRENT THERAPY: Complete resection required Randomization between 28 and 40 days after surgery required