Background: Non-small-cell lung carcinoma (NSCLC) as the most common type of lung cancer has the most leading mortality rate among other cancers. Diabetes mellitus is one of the most common comorbidities of this disease. Metformin is a conventional anti-diabetic drug that is evaluated in various studies as an anti-cancer agent. This study was an updated systematic review and meta-analysis evaluating the effect of metformin on NSCLC. Materials and Methods: A systematic search was conducted through PubMed/Medline, EMBASE, and Cochrane library databases and all retrospective studies with the title the effect of metformin on the non-small cell lung cancer were collected. Statistical analyses were carried out using either random-effects or fixed-effects models according to the heterogeneity examined by I² statistics and assessing Hazard Ratio of overall survival (OS) using Revman version 5 software. Result: Fourteen studies involving 3164 patients were included in the current meta-analysis. The pooled hazard ratio (HR) of comparison of overall survival (OS) between metformin user diabetic patients and diabetic patients without a history of using metformin was 0.87 (95 % CI 0.74–1.02; P = 0.08). Sub-group analysis showed that when studies were divided by region the HR of OS for Asia was 0.77 (95 % CI 0.65–0.90; P = 0.001), 1.11 (95 % CI 0.72–1.71; P = 0.64) for USA, and 0.86 (95 % CI 0.57–1.30; P = 0.47) for Europe. Conclusion: The use of metformin beside radiotherapy in patients with type 2 diabetes may be associated with a good prognosis. While this impact was just significantly seen in Asian studies.