Electronic Health Records (EHR) contain rich information about patients that can be used to improve decision support systems that assist Health Care workers. Personalized care is a concept that is gaining much acceleration as it talks about tailoring the treatment of an individual by proactively identifying possible risks. One approach used in personalized care is to identify similar patients to plan customized treatment. This paper reports work done to identify patient similarity from EHR records to form clusters of similar patients. Paper discusses the proof of concept that uses Jaccard Similarity and the Sorensen-Dice Similarity Index to find patient similarity. The similarity score calculated is used to build clusters that were optimized using the Elbow Method and Silhouette Index. The quantitative analysis of metrics suggests that Jaccard Index with Silhouette Index and Sorensen-Dice Similarity Index with the Elbow Method gave better clusters. The EHR of the patients in a cluster can be used to derive insights that can guide personalized care.