Studies examining the relation of body mass index (BMI) and mortality in patients with lung cancer have shown diverse results. We conducted a meta-analysis to investigate the association using all available studies from January 1982 to October 2016. PubMed and EMBASE were searched to identify relevant studies. We calculated the summary hazard ratio (HR) and 95% confidence interval (CI) using random effects model. The dose-response relationship was assessed by random effects meta-regression model. Fifty-five articles from 51 studies involving 3 152 552 subjects (males, 54.8%) were included. The pooled results suggested that on average a high BMI decreased risk of death from lung cancer or all-cause. Each 5 kg/m2 increase in BMI had a 12% lower risk of lung cancerspecific mortality (HR = 0.88, 95% CI: 0.75-1.02, P = 0.09) and a 14% lower risk of all-cause mortality (HR = 0.86, 95% CI: 0.77-0.96, P < 0.01). When stratifying by ethnicity, each 5 kg/m2 increase in BMI was associated with 22% and 28% reduction, respectively, in the risk of lung cancer-specific mortality (P < 0.01) and all-cause mortality (P < 0.01) in Asians, but no association was found in Westerners (P = 0.51 and P = 0.53, respectively). In conclusion, lung cancer patients with a higher BMI have a longer survival than those with a lower BMI. Considering the significant heterogeneity between included studies, future studies are needed to confirm these findings.