Myocardial infarction (MI), also known as heart attack, is the leading cause of death - about 452,000 per year - in US. It often occurs due to the occlusion of coronary arteries, thereby leading to the insufficient blood and oxygen supply that damage cardiac muscle cells. Because the blood vessels are all over the heart, MI can happen at different spatial locations (e.g., anterior and inferior portions) of the heart. The spatial location of diseases causes the variable excitation and propagation of cardiac electrical activities in space and time. Most of previous studies focused on the relationships between disease and time-domain biomarkers (e.g., QT interval, ST elevation/depression, heart rate) from 12-lead ECG signals. Few, if any, previous approaches have investigated how the spatial location of diseases will alter cardiac vectorcardiogram (VCG) signals in both space and time. This paper presents a novel warping approach to quantify the dissimilarity of disease-altered patterns in 3-lead spatiotemporal VCG signals. The hypothesis testing shows there are significant spatiotemporal differences between healthy controls (HC), MI-anterior, MI-anterior-septal, MI-anterior-lateral, MI-inferior, and MI-inferior-lateral. Further, we optimize the embedding of each functional recording as a feature vector in the high-dimensional space that preserves the dissimilarity distance matrix. This novel spatial embedding approach facilitates the construction of classification models and yields an accuracy of 94.7% for separating MIs and HCs and an accuracy of 96.5% for anterior-related MIs and inferior-related MIs.