This thesis presents a method of clustering ECG morphologies for the identification of individual ECG features in congenital heart disease. Clustering is performed on the computed heart dipole moment magnitude using k-medoids clustering with variants of dynamic time warping. The method is applied to both synthetic data and patient data with different parameter values for classic and derivative dynamic time warping. A deterministic k-medoids algorithm demonstrates poor clustering results on both data sets, but an iterative approach with random initialization shows marked improvement. The synthetic data clusters are generally well-defined with the expected number of clusters. Though the patient data derivative results are inconclusive, upon closer examination, the clustering results from classic dynamic time warping with a small warping window seem sensible. Through this project, the groundwork is laid for the future classification of ECG recordings and the development of predictive models in patients with congenital heart disease.