The most familiar cancer that occurs usually for men and women is lung cancer. The survival rate for the cancer patient can be increased by detecting the occurrence of cancer in earlier stages. But, the early detection of lung cancer is a challenging problem due to the structure of the cancerous cells. This paper presents segmentation of the suspected lung nodules from the input Computed Tomography (CT) image by K-means clustering algorithm and classification by Artificial Neural Network (ANN). Initially the input CT image is preprocessed to remove noise. Then, the suspected lung nodules are segmented from the input CT image using K-means clustering algorithm. For the suspected nodules, the features are extracted and given as input to the ANN, which classifies whether the suspected nodules are benign (normal) or malignant (cancerous) in early stages.