A case-control study was conducted to investigate the relationship between diet and the risk of lung cancer among women non-smokers and to compare with women smokers in the same population. Data collected by personal interviews from 435 microscopically confirmed cases and 1710 controls were analysed using unconditional logistic regression. In addition to results for all study subjects, associations between diet and lung cancer risk were compared between two highly contrasting groups: smokers (odds ratio (OR) 7.03) and non-smokers (OR 1.00). A protective effect of frequent (daily or several times per week) black tea drinking appeared among non-smoking women (OR 0.65, 95% confidence interval (CI) 0.43-0.99). Among smoking women, protective effects were observed for frequent intake of milk/dairy products (OR 0.56, 95% CI 0.32-0.96), coffee (OR 0.47, 95% CI 0.25-0.88), and wine consumption (daily or weekly OR 0.60, 95% CI 0.37-0.98; monthly OR 0.60, 95% CI 0.39-0.94). Inverse associations with the risk appeared for physical exercise for smokers only, and for the body mass index both among non-smoking and smoking women. Some items of diet may contribute to variation in risk among women in the Czech Republic; their importance seems to vary in relation to their status in smoking, the dominant factor in the aetiology of lung cancer.