Lung cancer is one of the most prevalent cancers in the world and a leading cause of mortality. It causes due to the uncontrollable proliferation of malignant cells in the lungs. The likelihood of curing lung cancer can be increased by early detection and treatment of the disease in its early stages. As a result of this, practitioners find computer assisted diagnosis helpful in accurately identifying the cancerous cells. The integration of machine learning with image processing techniques has been heavily incorporated into numerous computer-aided methods, and they have proven to be extremely effective. The aim of this research is to outline a clear procedure for detecting nodules using image enhancement techniques on computed tomography images that were obtained from the LIDC IDRI dataset, and the use of machine learning algorithm to categorize those nodules into two classes: benign and malignant. Our suggested model stands out from other proposals since it focuses on early detection of cancer nodule and XGBoost outperforms other machine learning algorithm in classifying identified nodules with an accuracy of 91%.